auliaadila commited on
Commit
d1fc3f8
1 Parent(s): f7c1dc7

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +12 -0
  3. vocab.json +32 -0
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "[UNK]",
11
+ "word_delimiter_token": "|"
12
+ }
vocab.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 24,
3
+ "[PAD]": 29,
4
+ "[UNK]": 28,
5
+ "a": 3,
6
+ "b": 0,
7
+ "c": 13,
8
+ "d": 12,
9
+ "e": 27,
10
+ "f": 17,
11
+ "g": 4,
12
+ "h": 22,
13
+ "i": 7,
14
+ "j": 19,
15
+ "k": 10,
16
+ "l": 20,
17
+ "m": 1,
18
+ "n": 15,
19
+ "o": 14,
20
+ "p": 2,
21
+ "q": 21,
22
+ "r": 18,
23
+ "s": 9,
24
+ "t": 11,
25
+ "u": 16,
26
+ "v": 6,
27
+ "w": 23,
28
+ "x": 26,
29
+ "y": 5,
30
+ "z": 25,
31
+ "|": 8
32
+ }